Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
Nanbeige-16B-Base-32K-GPTQ
like
1
Text Generation
Transformers
Safetensors
English
Chinese
nanbeige
llm
custom_code
4-bit precision
gptq
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Use this model
gptq-4bit-32g-actorder_True
Nanbeige-16B-Base-32K-GPTQ
/
quantize_config.json
TheBloke
GPTQ model commit
1695acb
6 months ago
raw
history
blame
196 Bytes
{
"bits"
:
[
4
]
,
"group_size"
:
[
32
]
,
"damp_percent"
:
[
0.1
]
,
"desc_act"
:
[
true
]
,
"sym"
:
true
,
"true_sequential"
:
true
}